Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (month
    -0.07
     Mol
    -0.06
    аря
    -0.06
     sektör
    -0.06
    ήλ
    -0.06
     Sachs
    -0.06
     harms
    -0.06
     rift
    -0.06
     cate
    -0.06
    ежать
    -0.06
    POSITIVE LOGITS
    .system
    0.06
     커
    0.06
    हम
    0.06
    />
    0.06
    ewater
    0.06
    flag
    0.06
    uct
    0.06
    Conclusion
    0.06
     █
    0.06
     св
    0.06
    Act Density 0.148%

    No Known Activations